ForgeCode - Worlds #1 Coding Agent

Code • Refactor • Debug • Test • Document

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

Opus 4.8 support has been updated in `v2.13.3`. Let us know if you face any issues.

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

We’re working with Termbench to get our submission verified.

As part of the process, the team has agreed to take down our older submissions.

SPOILER ALERT: Once verified, this will be our highest score yet, beating all our previous submissions!

[Laurids 🇪🇺🇺🇦🇵🇸 @lauridskern]

I built the open source codex app!

One of my favorite features is “Workspaces” - reusable multi-chat layouts you can save and switch between depending on the task.

Built on top of @forgecodehq

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

@AriesTheCoder @claudeusmaximus https://t.co/HF2fCxGmwS

[Waqas @Waqas171288]

Have a look at the leaderboard in terminal bench @forgecodehq really shining. Codex with gpt5.5 hits 82% whereas forgecode hits 81.80% with gpt5.4.

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

This is why ForgeCode invests heavily in prompt caching.

In one workspace over the last 7 days on Opus 4.7

- 407M: input tokens
- 382.9M: cache-read tokens
- 98.1%: cache read ratio
- 22.9×: write amortization

Amortization = tokens read back per token written to cache.
So every 1 token cached was reused ~23 times.

At public API pricing, that’s ~$2,035 without caching vs ~$333 with 5-minute caching.

~$1.7K saved in input-token cost alone.

[Tensorlake @tensorlake]

Is the real bottleneck for AI agents the model—or the harness?

Terminal-Bench 2.0 suggests it might be the latter. ForgeCode ranks #1 among open-source harnesses, showing how much performance you can unlock without changing the model—just by improving how it uses tools.

In ForgeCode’s case, the gains come from better tool orchestration and execution.

Learn more: https://t.co/hN2RZZJDCs

[AriesTheCoder @AriesTheCoder]

Days ago, I was checking out the once VERY relevant terminal bench. I kept seeing this Agent called @forgecodehq always in the top 5.

Decided to try it and never looked back. It's now my daily ai-enhanced terminal.

Feature packed, but not stuffed to the gills. I love it!

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

@JustinPBarnett @tiberriver256 Please try with these
Recommended Settings
1. GPT 5.5 (Medium).
2. GPT 5.4 (High)
3. GPT 5.3-codex (Xhigh)

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

@JustinPBarnett @tiberriver256 Hi @JustinPBarnett can u tell us more about the slowness? Platform, model etc.

[Tushar Mathur @tusharmath]

After 2 months our #1 rank on Termbench was finally broken by a worth competitor (by 0.2%) 🙌

If someone from @OpenAI can help us in getting unrestricted API access, that'd be great! We'd love to run to on @forgecodehq and share notes 😇

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

@im_hash_im Can you share a screenshot or join our discord, we'd be more than happy to help.

Discord: https://t.co/gcESQTgvqu

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

Configure a symbol + conversion rate to display costs in your local currency.

Useful if you need a more accurate sense of the real value of the work being produced.

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

@ChamalkaAI Please share it with us, we'll fix it right away.

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

@mkXomj Great to hear that.
Feel free to hop on to our discord, we'd be happy to help if you need anything.

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

Continuing our commitment to open-sourcing our TermBench improvements, we’re shipping another update.

In `v2.8.0`, the `task` tool is now publicly available.

`task` enables the main agent to delegate work to specialized, user-defined agents, keeping the context window focused and efficient.

Example: hit a Rust compile error? Invoke a Rust-specific sub-agent to handle compiler runs, rules, and debugging in isolation.

Enabled by default.

https://t.co/7Zj1Gdavx5

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

File edit tooling was heavily optimized to improve performance on TermBench 2.0.

In our latest release (v2.7.0), the multi-edit tool is now GA.

https://t.co/uVGYewg55A

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

@wiedymi Yes, and also made it faster! Feel free to hop on our discord, we'd be more than happy to help!

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

@TheoLBorges @theo Looking forward to getting feedback.

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

@devon_chaine @theo We talk about how we achieved SOTA in our blog

https://t.co/AA319wWxwT

[ForgeCode - Worlds #1 Coding Agent @forgecodehq]

@Daniel_Kelly89 Join our discord, we'd be more than happy to help!